Search

Deep learning-based incipient fault diagnostic techniques have achieved surprisingly well in wind turbines. Due to component failures, wind turbines must undergo active maintenance, substantially influencing revenue and power generation. Unfortunately, there are consistently uneven data distributions between samples with faults and those without faults, resulting in incorrect fault classification. Wind turbine fault classification has a significant data imbalance problem, compromising learning attention for majority and minority classes. Machine learning methodologies based on Generative Adversarial Networks (GAN), over-sampling, and under-sampling techniques for generating synthetic data have been widely employed to address the imbalance data problem. However, the traditional synthetic minority oversampling technique (SMOTE) accomplishes oversampling using linear interpolation between close minority class samples, which could be confusing, subpar, and indistinguishable from the majority class. This study suggests combining over and under-sampling using adaptive SMOTE and edited nearest neighbors (ASMOTE-ENN) that incorporate over-sampling with adaptive SMOTE and under-sampling with ENN to improve the quality of the generated samples. With this resampling technique, noise in an imbalanced dataset is reduced on three levels by using an adaptive nearest neighbor selection algorithm to find the nearest neighbors that are visible. Then use SMOTE to create samples that precisely fall into the minority class, and later use the ENN technique to eliminate instances that contribute to noise afterwards. Resampling data created by combining over- and under-sampling approaches to match the data distribution over all classes is the foundation of the suggested method's efficacy. A hybrid ensemble method is used for effective classification, including boosting, bagging, and stacking techniques. The original unbalanced and balanced data using the ASMOTE-ENN algorithm were classified using the proposed hybrid ensemble method. The classification results show that the proposed strategy is more accurate than a few imbalanced fault diagnosis techniques. • To gain complete knowledge, characteristics of SCADA data are obtained using data analysis. • We present the adaptive SMOTE-ENN algorithm-based data resampling technique to deal with imbalanced data. • Create a hybrid ensemble classification technique to identify faulty and no-fault events effectively. • The results demonstrate that the suggested method outperforms the most popular ML techniques. [ABSTRACT FROM AUTHOR]

As substantial parts of process monitoring, fault classification techniques have been widely utilized in modern industries. However, most methods can only perform well under specific condition, which indicates that it is always difficult to ensure the classification efficiency for complex industrial processes using only one method. In this paper a weighted decision fusion system is proposed where an extended analytic hierarchy process (EAHP) structure is designed to give a comprehensive explanation for the weights assigned to the original fault classification results. Firstly, the fault category information is embedded in the EAHP structure, which makes it possible to consider both fault-wise and classifier-wise information in the fault classification. Secondly, an overall priority (OP) matrix is proposed to provide full prior knowledge for all classifiers. Different from previous researches, traditional OP vectors are replaced by the new-designed OP matrix which can contain more information about fault category. Thirdly, another confidence matrix is carried out to update the classification results. Compared with previous state-of-art, the confidence matrix can be adjusted according to the specific original classification result Finally, the effectiveness of the proposed method is verified by a numerical example and the Tennessee Eastman process (TEP) where the proposed decision fusion system shows superior fault classification results in both experiments. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) power generation is one of the remarkable energy types to provide clean and sustainable energy. Therefore, rapid fault detection and classification of PV modules can help to increase the reliability of the PV systems and reduce operating costs. In this study, an efficient PV fault detection method is proposed to classify different types of PV module anomalies using thermographic images. The proposed method is designed as a multi-scale convolutional neural network (CNN) with three branches based on the transfer learning strategy. The convolutional branches include multi-scale kernels with levels of visual perception and utilize pre-trained knowledge of the transferred network to improve the representation capability of the network. To overcome the imbalanced class distribution of the raw dataset, the oversampling technique is performed with the offline augmentation method, and the network performance is increased. In the experiments, 11 types of PV module faults such as cracking, diode, hot spot, offline module, and other classes are utilized. The average accuracy is obtained as 97.32% for fault detection and 93.51% for 11 anomaly types. The experimental results indicate that the proposed method gives higher classification accuracy and robustness in PV panel faults and outperforms the other deep learning methods and existing studies. • The Multi-scale network efficiently classifies photovoltaic panel anomalies. • Oversampling approach overcomes the imbalanced class distribution. • Multi-scale branches aim to improve the features extracted by each parallel block. • Proposed method is validated with a large dataset collected from six continents. [ABSTRACT FROM AUTHOR]

Abstract: This article studies if machine faults can be effectively determined in a reduced dimensional space. When faults occur in machines, machine vibration signals will deviate from its normal signal pattern. Such changes can be reflected in the features constructed from the machine signals. In this article, 13-dimension feature data set is constructed to represent different health conditions of machines, and unsupervised learning algorithms are introduced to deal with feature data sets for feature extraction and fault classification. A weighted local and global regressive mapping (WLGRM) algorithm is proposed for machine fault classification. Two synthetic fault data sets and two experimental data sets are employed to validate the effectiveness of the proposed approach. Comparative analysis with other unsupervised learning algorithms, such as local and global regressive mapping, locality preserving projection, Isomap, principal component analysis, and Sammon mapping, are reported. The results show that different machine faults can be classified, the degree of fault severity can be captured, and WLGRM can achieve better performance than other algorithms in most cases of machine fault classification. [Copyright &y& Elsevier]

Abstract: This paper proposes a new approach based on combined Wavelet Transform-Extreme Learning Machine (WT-ELM) technique for fault section identification (whether the fault is before or after the series capacitor as observed from the relay point), classification and location in a series compensated transmission line. This method uses the samples of fault currents for half cycle duration from the inception of fault. The features of fault currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and the extracted features are applied as inputs to ELMs for fault section identification, classification and location. The feasibility of the proposed method has been tested on a 400kV, 300km series compensated transmission line for all the ten types of faults using MATLAB simulink. On testing 28,800 fault cases with varying fault resistance, fault inception angle, fault distance, load angle, percentage compensation level and source impedance, the performance of the proposed method has been found to be quite promising. The results also indicate that the proposed method is robust to wide variation in system and operating conditions. [Copyright &y& Elsevier]

This work deals with robust dynamic probabilistic modeling and fault classification for process data. In dynamic processes, observed variables can be numerous in amount and correlated with each other in both variable-wise and time-wise. While multivariate statistical analysis methods such as principle component analysis (PCA) are widely used to handle variable-wise correlations and also for dimension reduction purpose, the time-wise correlation among process data is typically addressed by constructing dynamical models, e.g. time-series data model, state space model, etc. In this paper, the robust probabilistic principle component analysis (RPPCA) model is introduced for feature extraction from contaminated process data, suffered from outliers, disturbances, heave noises, etc. A dynamic Bayesian network (DBN) is then constructed, with incorporation of a mixture of Gaussian components for approximation of the non-Gaussian characteristics of latent variables. Based on the developed robust dynamic Bayesian network model, a fault classification scheme is proposed. To validate the effectiveness and feasibility of the new method, two well-known benchmark case studies are carried out. Simulation results show that robust dynamic method performs better in outlier contaminated situations, where the performance has been improved by 10%–20% in most cases. [ABSTRACT FROM AUTHOR]

In this paper, empirical Wavelet transform (EWT), Hilbert transform (HT) and weighted random vector functional link network (WRVFLN) are integrated for fault detection, classification, and location estimation in a series capacitor compensated double circuit transmission line (SCCDCTL). The full cycle current signals from the point of fault inception are decomposed using EWT to extract three band-limited modes (BLMs). The four efficacious instantaneous features namely energy, Shannon entropy, the standard deviation of the magnitude, and crest factor are computed from the Hilbert transformed array of the BLMs to construct the feature vector. A diagonal matrix W is computed from the zero sequence current of original six current signals as a weighting factor to categorize the ground fault accurately. Numerous faults are generated with a wide variation of the system conditions such as fault resistance, fault inception angle, fault distance, percentage compensation level, source impedance, line parameters, load angle, and inter-circuit fault in MATLAB/Simulink environments. An efficient WRVFLN computational intelligence technique is proposed to recognize and estimate the location of the faults by taking the extracted suitable feature vector with weight factor as an input. The performances of WRVFLN are compared with the recently developed advanced classifiers such as least-square support vector machine (LSSVM) and extreme learning machine (ELM) in the MATLAB interface. The lesser computational complexity, faster learning speed, superior classification accuracy, accurate fault location estimation, and short event detection time prove that the proposed EWTHT–WRVFLN method can be implemented in the real power system for online fault diagnosis. Finally, the developed system architecture is implemented on the reconfigurable digital field programmable gate array (FPGA) in ISE design suite 14.5 environments to verify the cogency of the proposed method in real-time. The feasibility of the proposed method is tested and validated by using the fast FPGA digital circuitry in a loop. • Empirical Wavelet Transform is used for series compensated lines for fault studies. • A weighted Random Vector Functional Link Network is used for fault classification and location. • A comparison with LS-SVM is presented in this paper to validate the superiority of WRVFLN. • Implementation of the WRVFLN using FPGA hardware exhibits the real-time capability of the new approach. [ABSTRACT FROM AUTHOR]